DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Why most AI tools fail at infrastructure troubleshooting

Why most AI tools fail at infrastructure troubleshooting

3
Comments
2 min read
The Hidden Costs of AI in Production (And How Developers Can Reduce Them)

The Hidden Costs of AI in Production (And How Developers Can Reduce Them)

Comments
4 min read
AI guardrails are not security boundaries

AI guardrails are not security boundaries

6
Comments 2
4 min read
Agents of Chaos: a field study of 16 agent failures (and refusals)

Agents of Chaos: a field study of 16 agent failures (and refusals)

Comments 1
4 min read
16 constitutional AI models built on a Chromebook

16 constitutional AI models built on a Chromebook

Comments 1
1 min read
I built a local-first movie recommender with Corrective-RAG (cited explanations, hybrid retrieval, runs entirely on Ollama)

I built a local-first movie recommender with Corrective-RAG (cited explanations, hybrid retrieval, runs entirely on Ollama)

Comments 1
1 min read
I Raised Gemma 4's Token Cap. The Dense Model Stopped Refusing.

Gemma 4 Challenge: Write about Gemma 4 Submission

I Raised Gemma 4's Token Cap. The Dense Model Stopped Refusing.

24
Comments 9
7 min read
Agent Series (5): Intent Recognition and Routing — Making Agents Actually Understand Users

Agent Series (5): Intent Recognition and Routing — Making Agents Actually Understand Users

2
Comments
11 min read
Fine-Tuning Large Language Models for Domain-Specific Applications

Fine-Tuning Large Language Models for Domain-Specific Applications

1
Comments 1
3 min read
AI Memory Needs an Authority Policy, Not Just More Context

AI Memory Needs an Authority Policy, Not Just More Context

Comments 2
7 min read
Build an LLM Router with pydantic-ai: Route Prompts to the Cheapest Model

Build an LLM Router with pydantic-ai: Route Prompts to the Cheapest Model

Comments 2
2 min read
AI Memory Should Decide What Context Is Allowed To Do

AI Memory Should Decide What Context Is Allowed To Do

Comments
5 min read
Open WebUI Desktop with llama.cpp, Ollama Multimodal App, & Optimized Gemma 4e4b

Open WebUI Desktop with llama.cpp, Ollama Multimodal App, & Optimized Gemma 4e4b

Comments
3 min read
Three Failures My AI Memory System Tested — And the Flaw It Revealed in Itself

Three Failures My AI Memory System Tested — And the Flaw It Revealed in Itself

Comments
6 min read
Agentic AI’s Token Debt: Why Multi-Step Tool Chains Blow Up Your Context Window And How Semantic Distillation Fixes the O(N ) Problem

Agentic AI’s Token Debt: Why Multi-Step Tool Chains Blow Up Your Context Window And How Semantic Distillation Fixes the O(N ) Problem

Comments
4 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.